Cs2K: Class-specific and Class-shared Knowledge Guidance for Incremental Semantic Segmentation

TL;DR

This paper introduces Cs2K, a novel guidance method for incremental semantic segmentation that balances class-specific and class-shared knowledge, improving performance on new and old classes.

Contribution

The paper proposes a combined approach using prototype-guided pseudo labeling, class adaptation, and weight-guided consolidation to enhance incremental segmentation.

Findings

Significant performance improvement on public datasets.

Effective balancing of old and new class segmentation.

Plug-and-play method adaptable to existing models.

Abstract

Incremental semantic segmentation endeavors to segment newly encountered classes while maintaining knowledge of old classes. However, existing methods either 1) lack guidance from class-specific knowledge (i.e., old class prototypes), leading to a bias towards new classes, or 2) constrain class-shared knowledge (i.e., old model weights) excessively without discrimination, resulting in a preference for old classes. In this paper, to trade off model performance, we propose the Class-specific and Class-shared Knowledge (Cs2K) guidance for incremental semantic segmentation. Specifically, from the class-specific knowledge aspect, we design a prototype-guided pseudo labeling that exploits feature proximity from prototypes to correct pseudo labels, thereby overcoming catastrophic forgetting. Meanwhile, we develop a prototype-guided class adaptation that aligns class distribution across datasets via learning old augmented prototypes. Moreover, from the class-shared knowledge aspect, we propose a weight-guided selective consolidation to strengthen old memory while maintaining new memory by integrating old and new model weights based on weight importance relative to old classes. Experiments on public datasets demonstrate that our proposed Cs2K significantly improves segmentation performance and is plug-and-play.